samson82-aiml/cricket-batting-coach

🏏 Cricket Batting Coach

A real-time cricket batting coach that uses computer vision to detect and analyze batting swings. Built with Streamlit and optimized for Hugging Face Spaces.

🚀 Live Demo


🎯 Features

• —Real-time Pose Detection: Uses MediaPipe for accurate pose tracking
• —Swing Analysis: Detects forward batting swings with speed and direction analysis
• —Live Video Processing: WebRTC-based video streaming for low-latency performance
• —Swing Counter: Tracks and displays swing count in real-time
• —Visual Feedback: Real-time overlay with swing detection indicators

🛠️ Technology Stack

• —Frontend: Streamlit
• —Video Processing: OpenCV, MediaPipe
• —Real-time Communication: WebRTC
• —Deployment: Hugging Face Spaces

📋 Requirements

• —Python 3.11 (for MediaPipe compatibility)
• —Webcam access
• —Modern web browser with WebRTC support

🚀 Quick Start

Local Development

1. 1.Clone the repository

   git clone https://github.com/samjosdev/cricket-batting-coach.git
   cd cricket-batting-coach

1. 1.Install dependencies

   pip install -r requirements.txt

1. 1.Run the application

   streamlit run app.py

1. 1.Open your browser Navigate to http://localhost:8501

Hugging Face Spaces Deployment

1. 1.Fork this repository
2. 2.Create a new Space on Hugging Face
3. 3.Go to Hugging Face Spaces
4. 4.Click "Create new Space"
5. 5.Choose "Streamlit" as the SDK
6. 6.Set the repository to your forked repo

1. 1.Configure the Space
2. 2.The Space will automatically detect the app.py file
3. 3.Dependencies will be installed from requirements.txt
4. 4.Python version will be set to 3.11

🎮 How to Use

1. 1.Start the Application
2. 2.Click "Start" to begin video processing
3. 3.Allow camera access when prompted

1. 1.Position Yourself
2. 2.Stand in front of the camera
3. 3.Ensure your full body is visible
4. 4.Hold a cricket bat or simulate batting motion

1. 1.Practice Your Swings
2. 2.Make forward batting swings
3. 3.The app will detect and count your swings
4. 4.Watch for the "SWING DETECTED!" indicator

1. 1.Monitor Your Progress
2. 2.Track your swing count in real-time
3. 3.Analyze swing speed and direction
4. 4.Reset counters as needed

🔧 Configuration

Python Version

The app is configured to use Python 3.11 for optimal MediaPipe compatibility:

• —.python-version: Specifies Python 3.11
• —runtime.txt: Alternative Python version specification

Dependencies

Key dependencies are specified in requirements.txt:

streamlit==1.28.1
streamlit-webrtc==0.47.1
opencv-python-headless==4.8.1.78
mediapipe==0.10.7
numpy==1.24.3
av==10.0.0

System Dependencies

Required system packages are specified in packages.txt:

libgl1-mesa-glx
libglib2.0-0
libsm6
libxext6
libxrender-dev
libgomp1

🎯 Swing Detection Algorithm

The app uses a sophisticated algorithm to detect cricket batting swings:

1. 1.Pose Tracking: MediaPipe tracks 33 body landmarks
2. 2.Wrist Movement: Monitors wrist position changes over time
3. 3.Speed Calculation: Computes movement speed between frames
4. 4.Direction Analysis: Determines swing direction (forward/backward)
5. 5.Threshold Filtering: Applies minimum speed and direction thresholds
6. 6.Cooldown System: Prevents double-counting of swings

Detection Parameters

• —Speed Threshold: 0.045 (minimum movement speed)
• —Direction Threshold: 0.005 (minimum forward motion)
• —History Length: 15 frames for analysis
• —Cooldown: 80 frames between detections

🐛 Troubleshooting

Common Issues

1. 1.Camera Not Working
2. 2.Ensure camera permissions are granted
3. 3.Try refreshing the page
4. 4.Check browser WebRTC support

1. 1.Swing Detection Issues
2. 2.Ensure good lighting
3. 3.Position yourself clearly in frame
4. 4.Make deliberate forward swings

1. 1.Performance Issues
2. 2.Close other browser tabs
3. 3.Use a modern browser (Chrome, Firefox, Safari)
4. 4.Ensure stable internet connection

Hugging Face Spaces Issues

1. 1.Build Failures
2. 2.Check Python version compatibility
3. 3.Verify all dependencies are available
4. 4.Review build logs for specific errors

1. 1.Runtime Errors
2. 2.Ensure MediaPipe version compatibility
3. 3.Check system dependency installation
4. 4.Verify WebRTC configuration

🤝 Contributing

1. 1.Fork the repository
2. 2.Create a feature branch (git checkout -b feature/amazing-feature)
3. 3.Commit your changes (git commit -m 'Add amazing feature')
4. 4.Push to the branch (git push origin feature/amazing-feature)
5. 5.Open a Pull Request

📝 License

This project is licensed under the MIT License - see the LICENSE file for details.

🙏 Acknowledgments

• —MediaPipe for pose detection
• —Streamlit for the web framework
• —OpenCV for computer vision
• —Hugging Face for deployment platform

📞 Support

If you encounter any issues or have questions:

1. 1.Check the Issues page
2. 2.Create a new issue with detailed information
3. 3.Include your browser, OS, and error messages

Happy Batting! 🏏